bier
bier copied to clipboard
Cleaned up reference implementation of BIER: Boosting Independent Embeddings Robustly.
hi, i run your code using CUB200 dataset, but i can't reappear result of recall@1(0.575). Can you give me more detail about configure of parameters, likely training batch size, labels-per-batch?...
Hi, Thanks for a nice contribution! Could you please share the routine for the evaluation on PKU VehicleId dataset? Or is it the same as you have for CUB-200-2011? We...
In your paper,"Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly" Why do you subtract mean value of imageNet for preprocessing the training images? Could you explain me specifically? thanks